I get a lot of meaning out of weights and source (without the training data), no... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		antiframe 5 days ago \| parent \| context \| favorite \| on: Kimi K2 Thinking, a SOTA open-source trillion-para... I get a lot of meaning out of weights and source (without the training data), not sure about you. Calling it meaningless seems like exaggeration.

mensetmanusman 5 days ago [–]

Can you change the weights to improve?

HarHarVeryFunny 5 days ago | | [–]

You can fine tune without the original training data, which for a large LLM is typically going to mean using LoRA - keeping the original weights unchanged and adding separate fine-tuning weights.

danielmarkbruce 1 day ago | | [–]

it's a bunch of numbers. Of course you can change them.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact